INDEX

Explanations

words related to moisture levels, specifically dry and wet conditions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÏģÎº

-0.16

ATCH

-0.15

maj

-0.15

ozilla

-0.15

agli

-0.15

ister

-0.15

ISTER

-0.14

eer

-0.14

-sized

-0.14

POSITIVE LOGITS

GMT

0.19

ening

0.19

ken

0.18

out

0.18

vore

0.17

(æ°´

0.16

sdale

0.16

lands

0.15

outs

0.15

ness

0.15

Activations Density 0.053%

words related to moisture levels, specifically dry and wet conditions

No Comments

No Known Activations